Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legislation or policies related to workplaces or schools

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Pastebin
    -0.85
    çīĪ
    -0.73
     Hits
    -0.71
     Pieces
    -0.70
    Lv
    -0.69
    Offline
    -0.68
     Wad
    -0.67
     Niet
    -0.67
    luck
    -0.66
     è£ıè
    -0.66
    POSITIVE LOGITS
     discriminate
    1.46
     discourage
    1.37
     encourage
    1.34
     forbid
    1.32
     prohibit
    1.31
     exclude
    1.31
     segreg
    1.30
     allow
    1.26
     punish
    1.26
     condone
    1.23
    Act Density 0.476%

    No Known Activations